def testGetVariableGivenNameScoped(self):
with self.test_session():
with tf.variable_scope('A'):
a = variables.variable('a', [5])
b = variables.variable('b', [5])
self.assertEquals([a], variables.get_variables_by_name('a'))
self.assertEquals([b], variables.get_variables_by_name('b'))
def testGetVariableGivenNameScoped(self):
with self.test_session():
with tf.variable_scope('A'):
a = variables.variable('a', [5])
b = variables.variable('b', [5])
self.assertEquals([a], variables.get_variables_by_name('a'))
self.assertEquals([b], variables.get_variables_by_name('b'))
def testGetVariablesByNameReturnsByValueWithoutScope(self):
with self.test_session():
a = variables.variable('a', [5])
matched_variables = variables.get_variables_by_name('a')
# If variables.get_variables_by_name returns the list by reference, the
# following append should persist, and be returned, in subsequent calls
# to variables.get_variables_by_name('a').
matched_variables.append(4)
matched_variables = variables.get_variables_by_name('a')
self.assertEquals([a], matched_variables)
def testReuseVariables(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.batch_norm(images, scale=True, scope='bn')
ops.batch_norm(images, scale=True, scope='bn', reuse=True)
beta = variables.get_variables_by_name('beta')
gamma = variables.get_variables_by_name('gamma')
self.assertEquals(len(beta), 1)
self.assertEquals(len(gamma), 1)
moving_vars = tf.get_collection('moving_vars')
self.assertEquals(len(moving_vars), 2)
def testReuseVariables(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.batch_norm(images, scale=True, scope='bn')
ops.batch_norm(images, scale=True, scope='bn', reuse=True)
beta = variables.get_variables_by_name('beta')
gamma = variables.get_variables_by_name('gamma')
self.assertEqual(len(beta), 1)
self.assertEqual(len(gamma), 1)
moving_vars = tf.get_collection('moving_vars')
self.assertEqual(len(moving_vars), 2)
def testGetVariablesByNameReturnsByValueWithoutScope(self):
with self.test_session():
a = variables.variable('a', [5])
matched_variables = variables.get_variables_by_name('a')
# If variables.get_variables_by_name returns the list by reference, the
# following append should persist, and be returned, in subsequent calls
# to variables.get_variables_by_name('a').
matched_variables.append(4)
matched_variables = variables.get_variables_by_name('a')
self.assertEquals([a], matched_variables)
def testCreateVariablesWithoutCenterWithoutScale(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.batch_norm(images, center=False, scale=False)
beta = variables.get_variables_by_name('beta')
self.assertEquals(beta, [])
gamma = variables.get_variables_by_name('gamma')
self.assertEquals(gamma, [])
moving_mean = tf.moving_average_variables()[0]
moving_variance = tf.moving_average_variables()[1]
self.assertEquals(moving_mean.op.name, 'BatchNorm/moving_mean')
self.assertEquals(moving_variance.op.name, 'BatchNorm/moving_variance')
def testCreateVariablesWithoutCenterWithoutScale(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.batch_norm(images, center=False, scale=False)
beta = variables.get_variables_by_name('beta')
self.assertEquals(beta, [])
gamma = variables.get_variables_by_name('gamma')
self.assertEquals(gamma, [])
moving_mean = tf.moving_average_variables()[0]
moving_variance = tf.moving_average_variables()[1]
self.assertEquals(moving_mean.op.name, 'BatchNorm/moving_mean')
self.assertEquals(moving_variance.op.name, 'BatchNorm/moving_variance')
def testCreateVariables(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.batch_norm(images, scale=True)
beta = variables.get_variables_by_name('beta')[0]
gamma = variables.get_variables_by_name('gamma')[0]
self.assertEquals(beta.op.name, 'BatchNorm/beta')
self.assertEquals(gamma.op.name, 'BatchNorm/gamma')
moving_mean = tf.get_collection('moving_vars')[0]
moving_variance = tf.get_collection('moving_vars')[1]
self.assertEquals(moving_mean.op.name, 'BatchNorm/moving_mean')
self.assertEquals(moving_variance.op.name, 'BatchNorm/moving_variance')
def testCreateVariablesWithScale(self):
height, width = 3, 3
with self.test_session():
images = tf.random_uniform((5, height, width, 3), seed=1)
ops.batch_norm(images, scale=True)
beta = variables.get_variables_by_name('beta')[0]
gamma = variables.get_variables_by_name('gamma')[0]
self.assertEqual(beta.op.name, 'BatchNorm/beta')
self.assertEqual(gamma.op.name, 'BatchNorm/gamma')
moving_mean = tf.moving_average_variables()[0]
moving_variance = tf.moving_average_variables()[1]
self.assertEqual(moving_mean.op.name, 'BatchNorm/moving_mean')
self.assertEqual(moving_variance.op.name,
'BatchNorm/moving_variance')
